pip install google-api-python-client

Requirement already satisfied: google-api-python-client in c:\programdata\anaconda3\lib\site-packages (2.113.0)
Requirement already satisfied: httplib2<1.dev0,>=0.15.0 in c:\programdata\anaconda3\lib\site-packages (from google-api-python-client) (0.22.0)
Requirement already satisfied: google-auth<3.0.0.dev0,>=1.19.0 in c:\programdata\anaconda3\lib\site-packages (from google-api-python-client) (2.26.2)
Requirement already satisfied: google-auth-httplib2>=0.1.0 in c:\programdata\anaconda3\lib\site-packages (from google-api-python-client) (0.2.0)
Requirement already satisfied: google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5 in c:\programdata\anaconda3\lib\site-packages (from google-api-python-client) (2.15.0)
Requirement already satisfied: uritemplate<5,>=3.0.1 in c:\programdata\anaconda3\lib\site-packages (from google-api-python-client) (4.1.1)
Requirement already satisfied: googleapis-common-protos<2.0.dev0,>=1.56.2 in c:\programdata\anaconda3\lib\site-packages (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5->google-api-python-client) (1.62.0)
Requirement already satisfied: protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0.dev0,>=3.19.5 in c:\programdata\anaconda3\lib\site-packages (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5->google-api-python-client) (4.25.2)
Requirement already satisfied: requests<3.0.0.dev0,>=2.18.0 in c:\programdata\anaconda3\lib\site-packages (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5->google-api-python-client) (2.31.0)
Requirement already satisfied: cachetools<6.0,>=2.0.0 in c:\programdata\anaconda3\lib\site-packages (from google-auth<3.0.0.dev0,>=1.19.0->google-api-python-client) (5.3.2)
Requirement already satisfied: pyasn1-modules>=0.2.1 in c:\programdata\anaconda3\lib\site-packages (from google-auth<3.0.0.dev0,>=1.19.0->google-api-python-client) (0.2.8)
Requirement already satisfied: rsa<5,>=3.1.4 in c:\programdata\anaconda3\lib\site-packages (from google-auth<3.0.0.dev0,>=1.19.0->google-api-python-client) (4.9)
Requirement already satisfied: pyparsing!=3.0.0,!=3.0.1,!=3.0.2,!=3.0.3,<4,>=2.4.2 in c:\programdata\anaconda3\lib\site-packages (from httplib2<1.dev0,>=0.15.0->google-api-python-client) (3.0.9)
Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in c:\programdata\anaconda3\lib\site-packages (from pyasn1-modules>=0.2.1->google-auth<3.0.0.dev0,>=1.19.0->google-api-python-client) (0.4.8)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\programdata\anaconda3\lib\site-packages (from requests<3.0.0.dev0,>=2.18.0->google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5->google-api-python-client) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in c:\programdata\anaconda3\lib\site-packages (from requests<3.0.0.dev0,>=2.18.0->google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5->google-api-python-client) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\programdata\anaconda3\lib\site-packages (from requests<3.0.0.dev0,>=2.18.0->google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5->google-api-python-client) (1.26.16)
Requirement already satisfied: certifi>=2017.4.17 in c:\programdata\anaconda3\lib\site-packages (from requests<3.0.0.dev0,>=2.18.0->google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5->google-api-python-client) (2023.11.17)
Note: you may need to restart the kernel to use updated packages.

pip install plotly

Requirement already satisfied: plotly in c:\programdata\anaconda3\lib\site-packages (5.18.0)
Requirement already satisfied: tenacity>=6.2.0 in c:\programdata\anaconda3\lib\site-packages (from plotly) (8.2.2)
Requirement already satisfied: packaging in c:\programdata\anaconda3\lib\site-packages (from plotly) (23.0)
Note: you may need to restart the kernel to use updated packages.

import googleapiclient.discovery

import pandas as pd
import matplotlib as pt
import numpy as np
import altair as alt
alt.data_transformers.enable('default', max_rows=None)
from altair import Chart, X, Y, Color, Scale
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
from bs4 import BeautifulSoup

ISO = []

for i in yt["Country"]:
    if i == "USA":
        ISO.append("USA")
    elif i == "CANADA":
        ISO.append("CAN")
    elif i == "UK":
        ISO.append("GBR")
    elif i == "FRANCE":
        ISO.append("FRA")
    elif i == "DENMARK":
        ISO.append("DNK")
    elif i == "INDIA":
        ISO.append("IND")
    elif i == "JAPAN":
        ISO.append("JPN")
    elif i == "SOUTH KOREA":
        ISO.append("KOR")
    elif i == "MEXICO":
        ISO.append("MEX")
    elif i == "RUSSIA":
        ISO.append("RUS")
    else:
        ISO.append("")
yt["ISO"] = ISO

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[5], line 3
      1 ISO = []
----> 3 for i in yt["Country"]:
      4     if i == "USA":
      5         ISO.append("USA")

NameError: name 'yt' is not defined

from datetime import datetime 

def changedate_formate(yt):
  split = yt.split('.')
  a = split[1]
  b = split[2]
  c = split[0]
  ''.join(a+b+c)
  return 

yt.info() #The trending date format can now be calculated

yt.dropna(inplace = True)
print(yt.isna().sum())
print(yt.shape)

Data Preparation

usa = pd.read_csv("D:\Odin class\youtube/USvideos.csv", encoding = "ISO-8859-1")
country = []
for i in usa["video_error_or_removed"]:
    if i == "FALSE":
        country.append("United States of America")
    else:
        country.append("USA")

usa["Country"] = country
usa.head(10)

	video_id	trending_date	title	channel_title	category_id	publish_time	tags	views	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	video_error_or_removed	description	Country
0	2kyS6SvSYSE	17.14.11	WE WANT TO TALK ABOUT OUR MARRIAGE	CaseyNeistat	22	2017-11-13T17:13:01.000Z	SHANtell martin	748374	57527	2966	15954	https://i.ytimg.com/vi/2kyS6SvSYSE/default.jpg	False	False	False	SHANTELL'S CHANNEL - https://www.youtube.com/s...	USA
1	1ZAPwfrtAFY	17.14.11	The Trump Presidency: Last Week Tonight with J...	LastWeekTonight	24	2017-11-13T07:30:00.000Z	last week tonight trump presidency|"last week ...	2418783	97185	6146	12703	https://i.ytimg.com/vi/1ZAPwfrtAFY/default.jpg	False	False	False	One year after the presidential election, John...	USA
2	5qpjK5DgCt4	17.14.11	Racist Superman | Rudy Mancuso, King Bach & Le...	Rudy Mancuso	23	2017-11-12T19:05:24.000Z	racist superman|"rudy"|"mancuso"|"king"|"bach"...	3191434	146033	5339	8181	https://i.ytimg.com/vi/5qpjK5DgCt4/default.jpg	False	False	False	WATCH MY PREVIOUS VIDEO ▶ \n\nSUBSCRIBE ► ...	USA
3	puqaWrEC7tY	17.14.11	Nickelback Lyrics: Real or Fake?	Good Mythical Morning	24	2017-11-13T11:00:04.000Z	rhett and link|"gmm"|"good mythical morning"|"...	343168	10172	666	2146	https://i.ytimg.com/vi/puqaWrEC7tY/default.jpg	False	False	False	Today we find out if Link is a Nickelback amat...	USA
4	d380meD0W0M	17.14.11	I Dare You: GOING BALD!?	nigahiga	24	2017-11-12T18:01:41.000Z	ryan|"higa"|"higatv"|"nigahiga"|"i dare you"|"...	2095731	132235	1989	17518	https://i.ytimg.com/vi/d380meD0W0M/default.jpg	False	False	False	I know it's been a while since we did this sho...	USA
5	gHZ1Qz0KiKM	17.14.11	2 Weeks with iPhone X	iJustine	28	2017-11-13T19:07:23.000Z	ijustine|"week with iPhone X"|"iphone x"|"appl...	119180	9763	511	1434	https://i.ytimg.com/vi/gHZ1Qz0KiKM/default.jpg	False	False	False	Using the iPhone for the past two weeks -- her...	USA
6	39idVpFF7NQ	17.14.11	Roy Moore & Jeff Sessions Cold Open - SNL	Saturday Night Live	24	2017-11-12T05:37:17.000Z	SNL|"Saturday Night Live"|"SNL Season 43"|"Epi...	2103417	15993	2445	1970	https://i.ytimg.com/vi/39idVpFF7NQ/default.jpg	False	False	False	Embattled Alabama Senate candidate Roy Moore (...	USA
7	nc99ccSXST0	17.14.11	5 Ice Cream Gadgets put to the Test	CrazyRussianHacker	28	2017-11-12T21:50:37.000Z	5 Ice Cream Gadgets|"Ice Cream"|"Cream Sandwic...	817732	23663	778	3432	https://i.ytimg.com/vi/nc99ccSXST0/default.jpg	False	False	False	Ice Cream Pint Combination Lock - http://amzn....	USA
8	jr9QtXwC9vc	17.14.11	The Greatest Showman | Official Trailer 2 [HD]...	20th Century Fox	1	2017-11-13T14:00:23.000Z	Trailer|"Hugh Jackman"|"Michelle Williams"|"Za...	826059	3543	119	340	https://i.ytimg.com/vi/jr9QtXwC9vc/default.jpg	False	False	False	Inspired by the imagination of P.T. Barnum, Th...	USA
9	TUmyygCMMGA	17.14.11	Why the rise of the robots won’t mean the en...	Vox	25	2017-11-13T13:45:16.000Z	vox.com|"vox"|"explain"|"shift change"|"future...	256426	12654	1363	2368	https://i.ytimg.com/vi/TUmyygCMMGA/default.jpg	False	False	False	For now, at least, we have better things to wo...	USA

india = pd.read_csv("D:\Odin class\youtube/INvideos.csv", encoding = "ISO-8859-1")
country = []
for i in india["video_error_or_removed"]:
    if i == "FALSE":
        country.append("India")
    else:
        country.append("INDIA")

india["Country"] = country
india.head(3)

	video_id	trending_date	title	channel_title	category_id	publish_time	tags	views	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	video_error_or_removed	description	Country
0	kzwfHumJyYc	17.14.11	Sharry Mann: Cute Munda ( Song Teaser) | Parmi...	Lokdhun Punjabi	1	2017-11-12T12:20:39.000Z	sharry mann|"sharry mann new song"|"sharry man...	1096327	33966	798	882	https://i.ytimg.com/vi/kzwfHumJyYc/default.jpg	False	False	False	Presenting Sharry Mann latest Punjabi Song Cu...	INDIA
1	zUZ1z7FwLc8	17.14.11	पीरियड्स के समय, प...	HJ NEWS	25	2017-11-13T05:43:56.000Z	पीरियड्स के समय|"प...	590101	735	904	0	https://i.ytimg.com/vi/zUZ1z7FwLc8/default.jpg	True	False	False	पीरियड्स के समय, प...	INDIA
2	10L1hZ9qa58	17.14.11	Stylish Star Allu Arjun @ ChaySam Wedding Rece...	TFPC	24	2017-11-12T15:48:08.000Z	Stylish Star Allu Arjun @ ChaySam Wedding Rece...	473988	2011	243	149	https://i.ytimg.com/vi/10L1hZ9qa58/default.jpg	False	False	False	Watch Stylish Star Allu Arjun @ ChaySam Weddin...	INDIA

uk = pd.read_csv("D:\Odin class\youtube/GBvideos.csv", encoding = "ISO-8859-1")
country = []
for i in uk["video_error_or_removed"]:
    if i == "FALSE":
        country.append("United Kingdom")
    else:
        country.append("UK")
        
uk["Country"] = country
uk.head(1)

	video_id	trending_date	title	channel_title	category_id	publish_time	tags	views	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	video_error_or_removed	description	Country
0	Jw1Y-zhQURU	17.14.11	John Lewis Christmas Ad 2017 - #MozTheMonster	John Lewis	26	2017-11-10T07:38:29.000Z	christmas|"john lewis christmas"|"john lewis"|...	7224515	55681	10247	9479	https://i.ytimg.com/vi/Jw1Y-zhQURU/default.jpg	False	False	False	Click here to continue the story and make your...	UK

yt_merge = pd.concat([usa, uk, india])
yt = yt_merge[['trending_date', 'category_id', 'tags', 'views', 'likes', 'dislikes', 'comment_count', 'description', 'Country']]

yt.to_csv (r'YouTube.csv', index = False, header=True)

yt = pd.read_csv("YouTube.csv", parse_dates=['trending_date'], engine='python', error_bad_lines=False)
yt.head() 

C:\Users\Admin\AppData\Local\Temp\ipykernel_1388\1473296237.py:1: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version. Use on_bad_lines in the future.


  yt = pd.read_csv("YouTube.csv", parse_dates=['trending_date'], engine='python', error_bad_lines=False)

	trending_date	category_id	tags	views	likes	dislikes	comment_count	description	Country
0	17.14.11	22	SHANtell martin	748374	57527	2966	15954	SHANTELL'S CHANNEL - https://www.youtube.com/s...	USA
1	17.14.11	24	last week tonight trump presidency|"last week ...	2418783	97185	6146	12703	One year after the presidential election, John...	USA
2	17.14.11	23	racist superman|"rudy"|"mancuso"|"king"|"bach"...	3191434	146033	5339	8181	WATCH MY PREVIOUS VIDEO ▶ \n\nSUBSCRIBE ► ...	USA
3	17.14.11	24	rhett and link|"gmm"|"good mythical morning"|"...	343168	10172	666	2146	Today we find out if Link is a Nickelback amat...	USA
4	17.14.11	24	ryan|"higa"|"higatv"|"nigahiga"|"i dare you"|"...	2095731	132235	1989	17518	I know it's been a while since we did this sho...	USA

yt.tail()

	trending_date	category_id	tags	views	likes	dislikes	comment_count	description	Country
117212	18.14.06	23	twinkle vaishnav comedy|"twinkle vaishnav"|"tw...	214378	3291	404	196	PRG Music & RDC Rajasthani presents फेकà...	INDIA
117213	18.14.06	24	flowers serials|"actress"|"malayalam serials"|...	406828	1726	478	1428	Flowers - A R Rahman Show,Book your Tickets He...	INDIA
117214	18.14.06	24	mazhavil manorama|"bhramanam full episode"|"gt...	386319	1216	453	697	Subscribe to Mazhavil Manorama now for your da...	INDIA
117215	18.14.06	24	tarang|"tarang tv"|"tarang tv online"|"tarang ...	130263	698	115	65	Nuabohu : Story of a rustic village girl who w...	INDIA
117216	18.14.06	24	Ee Nagaraniki Emaindi|"Ee Nagaraniki Emaindi T...	1278249	22466	1609	1205	Check out Ee Nagaraniki Emaindi Trailer #EeNag...	INDIA

yt.isnull().sum()

trending_date       0
category_id         0
tags                0
views               0
likes               0
dislikes            0
comment_count       0
description      1743
Country             0
dtype: int64

yt.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 117217 entries, 0 to 117216
Data columns (total 9 columns):
 #   Column         Non-Null Count   Dtype 
---  ------         --------------   ----- 
 0   trending_date  117217 non-null  object
 1   category_id    117217 non-null  int64 
 2   tags           117217 non-null  object
 3   views          117217 non-null  int64 
 4   likes          117217 non-null  int64 
 5   dislikes       117217 non-null  int64 
 6   comment_count  117217 non-null  int64 
 7   description    115474 non-null  object
 8   Country        117217 non-null  object
dtypes: int64(5), object(4)
memory usage: 8.0+ MB

unique_categoriesid = yt['category_id'].unique()
print(unique_categoriesid, sep= "," )

[22 24 23 28  1 25 17 10 15 27 26  2 19 20 29 43 30]

yt['category_id'] = yt.category_id.replace("1", "Film & Animation")
yt['category_id'] = yt.category_id.replace("2", "Autos & Vehicles")
yt['category_id'] = yt.category_id.replace("10", "Music")
yt['category_id'] = yt.category_id.replace("15", "Pets & Animals")
yt['category_id'] = yt.category_id.replace("17", "Sports")
yt['category_id'] = yt.category_id.replace("19", "Travel & Events")
yt['category_id'] = yt.category_id.replace("20", "Gaming")
yt['category_id'] = yt.category_id.replace('22','People & Blogs')
yt['category_id'] = yt.category_id.replace("23", "Comedy")
yt['category_id'] = yt.category_id.replace("24","Entertainment")
yt['category_id'] = yt.category_id.replace("25", "News & Politics")
yt['category_id'] = yt.category_id.replace("26", "Howto & Style")
yt['category_id'] = yt.category_id.replace("27", "Education")
yt['category_id'] = yt.category_id.replace("28", "Science & Technology")
yt['category_id'] = yt.category_id.replace("29", "Nonprofits & Activism")
yt['category_id'] = yt.category_id.replace("30", "Movies")
yt['category_id'] = yt.category_id.replace("43", "Shows")

yt.head(5)

	trending_date	category_id	tags	views	likes	dislikes	comment_count	description	Country
0	17.14.11	22	SHANtell martin	748374	57527	2966	15954	SHANTELL'S CHANNEL - https://www.youtube.com/s...	USA
1	17.14.11	24	last week tonight trump presidency|"last week ...	2418783	97185	6146	12703	One year after the presidential election, John...	USA
2	17.14.11	23	racist superman|"rudy"|"mancuso"|"king"|"bach"...	3191434	146033	5339	8181	WATCH MY PREVIOUS VIDEO ▶ \n\nSUBSCRIBE ► ...	USA
3	17.14.11	24	rhett and link|"gmm"|"good mythical morning"|"...	343168	10172	666	2146	Today we find out if Link is a Nickelback amat...	USA
4	17.14.11	24	ryan|"higa"|"higatv"|"nigahiga"|"i dare you"|"...	2095731	132235	1989	17518	I know it's been a while since we did this sho...	USA

# Assuming you have a mapping of category IDs to category names
category_mapping = {
    1: "Film & Animation",
    2: "Autos & Vehicles",
    10: "Music",
    15: "Pets & Animals",
    17: "Sports",
    19: "Travel & Events",
    20: "Gaming",
    22: "People & Blogs",
    23: "Comedy",
    24: "Entertainment",
    25: "News & Politics",
    26: "Howto & Style",
    27: "Education",
    28: "Science & Technology",
    29: "Nonprofits & Activism",
    30: "Movies",
    43: "Shows",
}

# Replace the 'category_id' values with corresponding category names
yt['category_id'] = yt['category_id'].replace(category_mapping)

# Display the DataFrame
print(yt.head(5))

  trending_date     category_id  \
0      17.14.11  People & Blogs   
1      17.14.11   Entertainment   
2      17.14.11          Comedy   
3      17.14.11   Entertainment   
4      17.14.11   Entertainment   

                                                tags    views   likes  \
0                                    SHANtell martin   748374   57527   
1  last week tonight trump presidency|"last week ...  2418783   97185   
2  racist superman|"rudy"|"mancuso"|"king"|"bach"...  3191434  146033   
3  rhett and link|"gmm"|"good mythical morning"|"...   343168   10172   
4  ryan|"higa"|"higatv"|"nigahiga"|"i dare you"|"...  2095731  132235   

   dislikes  comment_count                                        description  \
0      2966          15954  SHANTELL'S CHANNEL - https://www.youtube.com/s...   
1      6146          12703  One year after the presidential election, John...   
2      5339           8181  WATCH MY PREVIOUS VIDEO ▶ \n\nSUBSCRIBE ► ...   
3       666           2146  Today we find out if Link is a Nickelback amat...   
4      1989          17518  I know it's been a while since we did this sho...   

  Country  
0     USA  
1     USA  
2     USA  
3     USA  
4     USA  

yt.head()

	trending_date	category_id	tags	views	likes	dislikes	comment_count	description	Country
0	17.14.11	People & Blogs	SHANtell martin	748374	57527	2966	15954	SHANTELL'S CHANNEL - https://www.youtube.com/s...	USA
1	17.14.11	Entertainment	last week tonight trump presidency|"last week ...	2418783	97185	6146	12703	One year after the presidential election, John...	USA
2	17.14.11	Comedy	racist superman|"rudy"|"mancuso"|"king"|"bach"...	3191434	146033	5339	8181	WATCH MY PREVIOUS VIDEO ▶ \n\nSUBSCRIBE ► ...	USA
3	17.14.11	Entertainment	rhett and link|"gmm"|"good mythical morning"|"...	343168	10172	666	2146	Today we find out if Link is a Nickelback amat...	USA
4	17.14.11	Entertainment	ryan|"higa"|"higatv"|"nigahiga"|"i dare you"|"...	2095731	132235	1989	17518	I know it's been a while since we did this sho...	USA

unique_categoriesid = yt['category_id'].unique()
print(unique_categoriesid)

['People & Blogs' 'Entertainment' 'Comedy' 'Science & Technology'
 'Film & Animation' 'News & Politics' 'Sports' 'Music' 'Pets & Animals'
 'Education' 'Howto & Style' 'Autos & Vehicles' 'Travel & Events' 'Gaming'
 'Nonprofits & Activism' 'Shows' 'Movies']

# yt.dropna(inplace = True)
print(yt.isna().sum())
print(yt.shape)

trending_date       0
category_id         0
tags                0
views               0
likes               0
dislikes            0
comment_count       0
description      1743
Country             0
dtype: int64
(117217, 9)

yt.dropna(inplace = True)
print(yt.isna().sum())
print(yt.shape)

trending_date    0
category_id      0
tags             0
views            0
likes            0
dislikes         0
comment_count    0
description      0
Country          0
dtype: int64
(115474, 9)

from datetime import datetime 

def changedate_formate(yt):
  split = yt.split('.')
  a = split[1]
  b = split[2]
  c = split[0]
  ''.join(a+b+c)
  return 

yt.info() #The trending date format can now be calculated

<class 'pandas.core.frame.DataFrame'>
Int64Index: 115474 entries, 0 to 117216
Data columns (total 9 columns):
 #   Column         Non-Null Count   Dtype 
---  ------         --------------   ----- 
 0   trending_date  115474 non-null  object
 1   category_id    115474 non-null  object
 2   tags           115474 non-null  object
 3   views          115474 non-null  int64 
 4   likes          115474 non-null  int64 
 5   dislikes       115474 non-null  int64 
 6   comment_count  115474 non-null  int64 
 7   description    115474 non-null  object
 8   Country        115474 non-null  object
dtypes: int64(4), object(5)
memory usage: 8.8+ MB

Graphical Analysis

import plotly.graph_objects as go
from plotly.subplots import make_subplots
import plotly.offline as pyo

# Assuming yt is your DataFrame

fig = make_subplots()

for category_id, group in yt.groupby('category_id'):
    fig.add_trace(go.Bar(
        x=group['Country'],
        y=group['likes'],
        name=f'Category {category_id}'
    ))

fig.update_layout(
    title="YouTube Videos User Engagement by Countries (Likes)",
    barmode='overlay',
    xaxis=dict(title='Country'),
    yaxis=dict(title='Likes'),
    legend=dict(title='Category'),
)

# Show the plot
pyo.plot(fig, filename='youtube_engagement.html')

import plotly.graph_objects as go

# Assuming yt is your DataFrame

fig = go.Figure()

for category_id, group in yt.groupby('category_id'):
    fig.add_trace(go.Bar(
        x=group['Country'],
        y=group['likes'],
        name=f'Category {category_id}'
    ))

fig.update_layout(
    title="YouTube Videos User Engagement by Countries (Likes)",
    barmode='overlay',
    xaxis=dict(title='Country'),
    yaxis=dict(title='Likes'),
    legend=dict(title='Category'),
)

fig.show()

import plotly.express as px
df = px.data.iris()
fig = px.scatter(df, x="sepal_width", y="sepal_length", color="species", marginal_y="violin",
           marginal_x="box", trendline="ols", template="simple_white")
fig.show()

px.bar(yt, x = "Country", y = "likes",color="category_id", barmode='overlay', title = "YouTube Videos User Engagement by Countries (Likes)")

px.bar(yt, x = "Country", y = "dislikes",color="category_id", barmode='overlay', title = "YouTube Videos User Engagement by Countries (Dislikes)")

import plotly.graph_objs as go

fig = px.bar(yt.head(), x='category_id', y='views', title='YouTube Videos Views by Category',
             labels={'views': 'Number of Views', 'category_id': 'Video Category'},
             color='category_id')
print(fig)
if isinstance(fig, go.Figure):
    print("fig is a valid Plotly figure object.")
else:
    print("fig is not a valid Plotly figure object.")
    
fig.show()

px.boxplot(yt, x = "Country", y = "comment_count", title = "YouTube Videos User Engagement by Countries (Comment Count)")

import plotly.graph_objects as go
from plotly.subplots import make_subplots
import plotly.offline as pyo

# Assuming yt is your DataFrame

fig = make_subplots()

for category_id, group in yt.groupby('category_id'):
    fig.add_trace(go.Bar(
        x=group['Country'],
        y=group['likes'],
        name=f'Category {category_id}'
    ))

fig.update_layout(
    title="YouTube Videos User Engagement by Countries (Likes)",
    barmode='overlay',
    xaxis=dict(title='Country'),
    yaxis=dict(title='Likes'),
    legend=dict(title='Category'),
)

# Show the plot
pyo.plot(fig, filename='youtube_engagement.html')

'youtube_engagement.html'

import plotly.offline as pyo
fig = px.bar(yt, x="Country", y="likes", color="category_id", barmode='overlay', title="YouTube Videos User Engagement by Countries (Likes)")
pyo.plot(fig, filename='yt_engagement.html')

'yt_engagement.html'

import plotly.express as px
import pandas as pd

# Assuming yt is your original DataFrame
# Creating a smaller subset, e.g., the first 100 rows
small_subset_yt = yt.head(100)

# Plotting with the smaller subset
fig = px.bar(small_subset_yt, x="Country", y="likes", color="category_id", barmode='overlay', title="YouTube Videos User Engagement by Countries (Likes)")
fig.show()

import plotly.offline as pyo
fig = px.bar(yt, x="Country", y="likes", color="category_id", barmode='group', title="YouTube Videos User Engagement by Countries (Likes)")
pyo.plot(fig, filename='yt_engagement.html')
# fig = px.bar(yt, x="Country", y="likes", color="category_id", barmode='group', title="YouTube Videos User Engagement by Countries (Likes)")

'yt_engagement.html'

import plotly.express as px
import pandas as pd

# Assuming yt is your original DataFrame
# Creating a smaller subset, e.g., the first 100 rows
small_subset_yt = yt.head(100)

# Plotting with the smaller subset
fig = px.bar(small_subset_yt, x="Country", y="likes", color="category_id", barmode='overlay', title="YouTube Videos User Engagement by Countries (Likes)")
fig.show()

import plotly.express as px
import pandas as pd

# Assuming yt is your DataFrame with multiple countries
# Creating a smaller subset, e.g., the first 100 rows
small_subset_yt = yt.head(100)

# Plotting with the smaller subset
fig = px.bar(small_subset_yt, x="Country", y="likes", color="category_id", barmode='overlay',
             facet_col="Country", facet_col_wrap=5,  # Adjust the wrap parameter as needed
             title="YouTube Videos User Engagement by Countries (Likes)")
fig.show()

likes_by_category = yt.groupby('category_id')['likes'].sum().reset_index()

fig = px.bar(likes_by_category, x='category_id', y='likes', title='User Engagement by Category (Likes)',
             labels={'likes': 'Total Likes', 'category_id': 'Category'})

# Show the plot
fig.show()

dislikes_by_category = yt.groupby('category_id')['dislikes'].sum().reset_index()

# Plotting the bar chart
fig = px.bar(dislikes_by_category, x='category_id', y='dislikes', title='User Engagement by Category (Dislikes)',
             labels={'dislikes': 'Total Dislikes', 'category_id': 'Category'})

# Show the plot
fig.show()

# RESEARCH QUESTION 4. Which category has the highest number of user engagement on YouTube (comments)? 
comments_by_category = yt.groupby('category_id')['comment_count'].sum().reset_index()

# Plotting the bar chart
fig = px.bar(comments_by_category, x='category_id', y='comment_count', title='User Engagement by Category (Comments)',
             labels={'comment_count': 'Total Comments', 'category_id': 'Category'})

# Show the plot
fig.show()

trends_by_month = yt.groupby('trending_date').size().reset_index(name='total_trends')

# Plotting the bar chart
fig = px.bar(trends_by_month, x='trending_date', y='total_trends',
             title='Total Trends by Month', labels={'total_trends': 'Total Trends', 'trending_month': 'Month'})

# Show the plot
fig.show()

YouTube Trending Videos Analysis

conda install -c conda-forge wordcloud=1.6.0 

Retrieving notices: ...working... done
Collecting package metadata (current_repodata.json): ...working... done
Solving environment: ...working... unsuccessful initial attempt using frozen solve. Retrying with flexible solve.
Collecting package metadata (repodata.json): ...working... failed

Note: you may need to restart the kernel to use updated packages.

DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): conda.anaconda.org:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/r/notices.json HTTP/1.1" 404 None
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/main/notices.json HTTP/1.1" 404 None
DEBUG:urllib3.connectionpool:https://conda.anaconda.org:443 "GET /conda-forge/notices.json HTTP/1.1" 404 None
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/msys2/notices.json HTTP/1.1" 404 None
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): conda.anaconda.org:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): conda.anaconda.org:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/msys2/noarch/current_repodata.json HTTP/1.1" 304 0
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/main/noarch/current_repodata.json HTTP/1.1" 304 0
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/r/noarch/current_repodata.json HTTP/1.1" 304 0
DEBUG:urllib3.connectionpool:https://conda.anaconda.org:443 "GET /conda-forge/win-64/current_repodata.json HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/r/win-64/current_repodata.json HTTP/1.1" 304 0
DEBUG:urllib3.connectionpool:https://conda.anaconda.org:443 "GET /conda-forge/noarch/current_repodata.json HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/msys2/win-64/current_repodata.json HTTP/1.1" 304 0
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/main/win-64/current_repodata.json HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): conda.anaconda.org:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): conda.anaconda.org:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): repo.anaconda.com:443
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/r/noarch/repodata.json HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/msys2/win-64/repodata.json HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/main/noarch/repodata.json HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/msys2/noarch/repodata.json HTTP/1.1" 304 0
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/r/win-64/repodata.json HTTP/1.1" 304 0
DEBUG:urllib3.connectionpool:https://repo.anaconda.com:443 "GET /pkgs/main/win-64/repodata.json HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:https://conda.anaconda.org:443 "GET /conda-forge/noarch/repodata.json HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:https://conda.anaconda.org:443 "GET /conda-forge/win-64/repodata.json HTTP/1.1" 200 None

CondaSSLError: Encountered an SSL error. Most likely a certificate verification issue.

Exception: [SSL: DECRYPTION_FAILED_OR_BAD_RECORD_MAC] decryption failed or bad record mac (_ssl.c:2576)

from wordcloud import WordCloud

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
Cell In[4], line 1
----> 1 from wordcloud import WordCloud

ModuleNotFoundError: No module named 'wordcloud'

import pandas as pd
import numpy as np
import matplotlib as mpl
from matplotlib import pyplot as plt
import seaborn as sns

import warnings
from collections import Counter
import datetime
import wordcloud
import json

import sys
print(sys.executable)

C:\ProgramData\anaconda3\python.exe

 pip install wordcloud

Requirement already satisfied: wordcloud in c:\programdata\anaconda3\lib\site-packages (1.9.3)
Requirement already satisfied: numpy>=1.6.1 in c:\programdata\anaconda3\lib\site-packages (from wordcloud) (1.24.3)
Requirement already satisfied: pillow in c:\programdata\anaconda3\lib\site-packages (from wordcloud) (9.4.0)
Requirement already satisfied: matplotlib in c:\programdata\anaconda3\lib\site-packages (from wordcloud) (3.7.1)
Requirement already satisfied: contourpy>=1.0.1 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (1.0.5)
Requirement already satisfied: cycler>=0.10 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (4.25.0)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (1.4.4)
Requirement already satisfied: packaging>=20.0 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (23.0)
Requirement already satisfied: pyparsing>=2.3.1 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (3.0.9)
Requirement already satisfied: python-dateutil>=2.7 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (2.8.2)
Requirement already satisfied: six>=1.5 in c:\programdata\anaconda3\lib\site-packages (from python-dateutil>=2.7->matplotlib->wordcloud) (1.16.0)
Note: you may need to restart the kernel to use updated packages.

# Hiding warnings for cleaner display
warnings.filterwarnings('ignore')

# Configuring some options
%matplotlib inline
%config InlineBackend.figure_format = 'retina'
# If you want interactive plots, uncomment the next line
# %matplotlib notebook

#Basic configurations for improving visualization of graphs

PLOT_COLORS = ["#268bd2", "#0052CC", "#FF5722", "#b58900", "#003f5c"]
pd.options.display.float_format = '{:.2f}'.format
sns.set(style="ticks")
plt.rc('figure', figsize=(8, 5), dpi=100)
plt.rc('axes', labelpad=20, facecolor="#ffffff", linewidth=0.4, grid=True, labelsize=14)
plt.rc('patch', linewidth=0)
plt.rc('xtick.major', width=0.2)
plt.rc('ytick.major', width=0.2)
plt.rc('grid', color='#9E9E9E', linewidth=0.4)
plt.rc('font', family='Arial', weight='400', size=10)
plt.rc('text', color='#282828')
plt.rc('savefig', pad_inches=0.3, dpi=300)

india = pd.read_csv("D:\Odin class\youtube/INvideos.csv")

india.head()

	video_id	trending_date	title	channel_title	category_id	publish_time	tags	views	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	video_error_or_removed	description
0	kzwfHumJyYc	17.14.11	Sharry Mann: Cute Munda ( Song Teaser) | Parmi...	Lokdhun Punjabi	1	2017-11-12T12:20:39.000Z	sharry mann|"sharry mann new song"|"sharry man...	1096327	33966	798	882	https://i.ytimg.com/vi/kzwfHumJyYc/default.jpg	False	False	False	Presenting Sharry Mann latest Punjabi Song Cu...
1	zUZ1z7FwLc8	17.14.11	पीरियड्स के समय, पेट पर पति करता ऐसा, देखकर दं...	HJ NEWS	25	2017-11-13T05:43:56.000Z	पीरियड्स के समय|"पेट पर पति करता ऐसा"|"देखकर द...	590101	735	904	0	https://i.ytimg.com/vi/zUZ1z7FwLc8/default.jpg	True	False	False	पीरियड्स के समय, पेट पर पति करता ऐसा, देखकर दं...
2	10L1hZ9qa58	17.14.11	Stylish Star Allu Arjun @ ChaySam Wedding Rece...	TFPC	24	2017-11-12T15:48:08.000Z	Stylish Star Allu Arjun @ ChaySam Wedding Rece...	473988	2011	243	149	https://i.ytimg.com/vi/10L1hZ9qa58/default.jpg	False	False	False	Watch Stylish Star Allu Arjun @ ChaySam Weddin...
3	N1vE8iiEg64	17.14.11	Eruma Saani | Tamil vs English	Eruma Saani	23	2017-11-12T07:08:48.000Z	Eruma Saani|"Tamil Comedy Videos"|"Films"|"Mov...	1242680	70353	1624	2684	https://i.ytimg.com/vi/N1vE8iiEg64/default.jpg	False	False	False	This video showcases the difference between pe...
4	kJzGH0PVQHQ	17.14.11	why Samantha became EMOTIONAL @ Samantha naga ...	Filmylooks	24	2017-11-13T01:14:16.000Z	Filmylooks|"latest news"|"telugu movies"|"telu...	464015	492	293	66	https://i.ytimg.com/vi/kJzGH0PVQHQ/default.jpg	False	False	False	why Samantha became EMOTIONAL @ Samantha naga ...

india.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 37352 entries, 0 to 37351
Data columns (total 16 columns):
 #   Column                  Non-Null Count  Dtype 
---  ------                  --------------  ----- 
 0   video_id                37352 non-null  object
 1   trending_date           37352 non-null  object
 2   title                   37352 non-null  object
 3   channel_title           37352 non-null  object
 4   category_id             37352 non-null  int64 
 5   publish_time            37352 non-null  object
 6   tags                    37352 non-null  object
 7   views                   37352 non-null  int64 
 8   likes                   37352 non-null  int64 
 9   dislikes                37352 non-null  int64 
 10  comment_count           37352 non-null  int64 
 11  thumbnail_link          37352 non-null  object
 12  comments_disabled       37352 non-null  bool  
 13  ratings_disabled        37352 non-null  bool  
 14  video_error_or_removed  37352 non-null  bool  
 15  description             36791 non-null  object
dtypes: bool(3), int64(5), object(8)
memory usage: 3.8+ MB

india["description"] = india["description"].fillna(value="")

india.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 37352 entries, 0 to 37351
Data columns (total 16 columns):
 #   Column                  Non-Null Count  Dtype 
---  ------                  --------------  ----- 
 0   video_id                37352 non-null  object
 1   trending_date           37352 non-null  object
 2   title                   37352 non-null  object
 3   channel_title           37352 non-null  object
 4   category_id             37352 non-null  int64 
 5   publish_time            37352 non-null  object
 6   tags                    37352 non-null  object
 7   views                   37352 non-null  int64 
 8   likes                   37352 non-null  int64 
 9   dislikes                37352 non-null  int64 
 10  comment_count           37352 non-null  int64 
 11  thumbnail_link          37352 non-null  object
 12  comments_disabled       37352 non-null  bool  
 13  ratings_disabled        37352 non-null  bool  
 14  video_error_or_removed  37352 non-null  bool  
 15  description             37352 non-null  object
dtypes: bool(3), int64(5), object(8)
memory usage: 3.8+ MB

# Extract the year from the "trending_date" column using string manipulation
india["year"] = '20' + india["trending_date"].str[:2]

# Count the occurrences of each unique year
year_counts = india["year"].value_counts()

# Create a DataFrame from the Series
cdf = year_counts.reset_index()

# Rename the columns
cdf = cdf.rename(columns={"index": "year", "year": "No_of_videos"})

# Display the result
print("Years in which data was collected:")
print(cdf)

Years in which data was collected:
   year  No_of_videos
0  2018         28293
1  2017          9059

import matplotlib.pyplot as plt

# Assuming you have already executed the previous code to create the 'cdf' DataFrame

# Bar plot
plt.figure(figsize=(10, 6))
plt.bar(cdf["year"], cdf["No_of_videos"], color='skyblue')
plt.title('Number of Videos Collected Each Year')
plt.xlabel('Year')
plt.ylabel('Number of Videos')
plt.show()

india.describe()

	category_id	views	likes	dislikes	comment_count
count	37352.00	37352.00	37352.00	37352.00	37352.00
mean	21.58	1060477.65	27082.72	1665.08	2677.00
std	6.56	3184932.05	97145.10	16076.17	14868.32
min	1.00	4024.00	0.00	0.00	0.00
25%	23.00	123915.50	864.00	108.00	81.00
50%	24.00	304586.00	3069.00	326.00	329.00
75%	24.00	799291.25	13774.25	1019.25	1285.00
max	43.00	125432237.00	2912710.00	1545017.00	827755.00

We note from the table above that The average number of viewson a trending video is 1,060,477. The median value for the number of views is 304,586 , which means that half the trending videos have views that are less than that number, and the other half have views larger than that number. The average number of likes on a trending video is 27,082 , while the average number of dislikes is 1,665. The average comment count is 2,677 while the median is 329.

import matplotlib.pyplot as plt

# Assuming you have a DataFrame named 'df'
# and the "views" column contains numerical data

# Specify the bin edges for the histogram
bin_edges = range(0, int(india["views"].max()) + 10000000, 10000000)

# Plot the histogram
plt.figure(figsize=(10, 6))
plt.hist(india["views"], bins=bin_edges, color='skyblue', edgecolor='black')
plt.title('Distribution of Views in Video Data')
plt.xlabel('Number of Views')
plt.ylabel('Number of Videos')
plt.xticks(bin_edges)  # Set x-axis ticks to match bin edges
plt.show()

plt.rc('figure.subplot', wspace=0.9)
fig, ax = plt.subplots()
_ = sns.distplot(india["likes"], kde=False, 
                 color=PLOT_COLORS[4], hist_kws={'alpha': 1}, 
                 bins=np.linspace(0, 6e6, 61), ax=ax)

_ = ax.set(xlabel="Likes", ylabel="No. of videos")
_ = plt.xticks(rotation=90)

fig, ax = plt.subplots()
_ = sns.distplot(india[india["likes"] <= 1e5]["likes"], kde=False, 
                 color=PLOT_COLORS[4], hist_kws={'alpha': 1}, ax=ax)
_ = ax.set(xlabel="Likes", ylabel="No. of videos")

Comment Count Histogram

fig, ax = plt.subplots()
_ = sns.distplot(india["comment_count"], kde=False, rug=False, 
                 color=PLOT_COLORS[4], hist_kws={'alpha': 1}, ax=ax)
_ = ax.set(xlabel="Comment Count", ylabel="No. of videos")

Do the trending video titles contain captitalized words?

def contains_capitalized_word(s):
    for w in s.split():
        if w.isupper():
            return True
    return False


india["contains_capitalized"] = india["title"].apply(contains_capitalized_word)

value_counts = india["contains_capitalized"].value_counts().to_dict()
fig, ax = plt.subplots()
_ = ax.pie([value_counts[False], value_counts[True]], labels=['No', 'Yes'], 
           colors=[PLOT_COLORS[4], '#ffa600'], textprops={'color': '#040204'}, startangle=45)
_ = ax.axis('equal')
_ = ax.set_title('Capitalized Word?')